chore: bump version to 6.0.0-Beta.2

**What's New in Beta.2:**

Builds on Beta.1 with critical enforcement fixes and learning feedback loop.

**From craftedcall production testing:**
- workflow.xml: Mandatory Task agent delegation (prevents context degradation)
- step-enforcement.xml: Centralized enforcement rules
- workflow-executor.md: Dedicated workflow execution agent
- ALL-STEPS-EMBEDDED.md: All steps in one file (prevents skipping)
- Per-task checkbox enforcement with auto-fix retry
- Pre-commit verification with auto-populate
- ONE canonical filename format

**From GSDMAD development:**
- Automated learning feedback loop (Step 1b + 12)
- Agent reasoning for playbook selection
- Self-reflection for pattern extraction
- Playbook system (Phase 1: markdown + frontmatter)

All 352 tests passing. Production-ready.

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@jonahschulte/bmad-method",
-  "version": "6.0.0-Beta.1",
+  "version": "6.0.0-Beta.2",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@jonahschulte/bmad-method",
-      "version": "6.0.0-Beta.1",
+      "version": "6.0.0-Beta.2",
       "license": "MIT",
       "dependencies": {
         "@clack/prompts": "^0.11.0",

package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@jonahschulte/bmad-method",
-  "version": "6.0.0-Beta.1",
+  "version": "6.0.0-Beta.2",
   "description": "Breakthrough Method of Agile AI-driven Development (Enhanced with TDD, intelligent multi-agent review, and production-hardened enforcement)",
   "keywords": [
     "agile",